import pandas as pd  #for data manipulation operations
import numpy as np  #for numeric operations on data
import seaborn as sns  #for data visualization operations
import matplotlib.pyplot as plt  #for data visualization operations
from sklearn.preprocessing import LabelEncoder # for encoding
from sklearn.preprocessing import MinMaxScaler, RobustScaler, StandardScaler #for standardization
import plotly.express as px
import plotly.graph_objects as go
import plotly.io as pio
import scipy.stats as st

#from markupsafe import escape
#!pip install pandas-profiling
#import pandas_profiling

from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score
from sklearn.metrics import confusion_matrix, accuracy_score, classification_report
from sklearn.metrics import accuracy_score
from sklearn.metrics import roc_auc_score, roc_curve
from sklearn import model_selection
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import GradientBoostingClassifier
#!pip install lightgbm
# from lightgbm import LGBMClassifier

#ignore warnings
import warnings
warnings.filterwarnings("ignore")

#see model parametres
from sklearn import set_config
set_config(print_changed_only = False)

# Đọc file winequality-red.csv
wine_data = pd.read_csv("winequality-red.csv")

# wine_data.head(5)

wine_df = wine_data.copy()
wine_df.head(n = 10).style.background_gradient(cmap = "Purples_r")

wine_df.shape

(1599, 12)

#Show the top rows of the dataframe
wine_data.head()

# Display the last five rows of the dataframe.
wine_data.tail()

wine_data.columns

Index(['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
       'pH', 'sulphates', 'alcohol', 'quality'],
      dtype='object')

wine_df.columns = [s.strip().replace(' ', '_') for s in wine_data.columns]
wine_df.columns

Index(['fixed_acidity', 'volatile_acidity', 'citric_acid', 'residual_sugar',
       'chlorides', 'free_sulfur_dioxide', 'total_sulfur_dioxide', 'density',
       'pH', 'sulphates', 'alcohol', 'quality'],
      dtype='object')

wine_df.describe().T.style.background_gradient(cmap = "magma")

wine_df.dtypes

fixed_acidity           float64
volatile_acidity        float64
citric_acid             float64
residual_sugar          float64
chlorides               float64
free_sulfur_dioxide     float64
total_sulfur_dioxide    float64
density                 float64
pH                      float64
sulphates               float64
alcohol                 float64
quality                   int64
dtype: object

print(wine_df.isnull().sum())

fixed_acidity           0
volatile_acidity        0
citric_acid             0
residual_sugar          0
chlorides               0
free_sulfur_dioxide     0
total_sulfur_dioxide    0
density                 0
pH                      0
sulphates               0
alcohol                 0
quality                 0
dtype: int64

fig, axes = plt.subplots(1, 3, figsize = (40, 10))

sns.histplot(ax = axes[0], x = wine_df["fixed_acidity"],
             bins = 10,
             kde = True,
             color = "#CA96EC").set(title = "Distribution of 'fixed_acidity'")

sns.histplot(ax = axes[1], x = wine_df["volatile_acidity"],
             bins = 10,
             kde = True,
             color = "#A163CF").set(title = "Distribution of 'volatile_acidity'")

sns.histplot(ax = axes[2], x = wine_df["citric_acid"],
             bins = 10,
             kde = True,   
             color = "#29066B").set(title = "Distribution of 'citric_acid'")

plt.show()

fig, axes = plt.subplots(1, 3, figsize=(40, 10))

sns.histplot(ax = axes[0], x = wine_df["alcohol"],
             bins = 10,    
             kde = True,
             cbar = True,
             color = "#641811").set(title = "Distribution of 'alcohol'");

sns.histplot(ax = axes[1], x = wine_df["residual_sugar"],
             bins = 10,
             kde = True,
             cbar = True,
             color = "#EB548C").set(title = "Distribution of 'residual_sugar'");

sns.histplot(ax = axes[2], x = wine_df["chlorides"],
             bins = 10,
             kde = True,   
             cbar = True,
             color = "#EC96E0").set(title = "Distribution of 'chlorides'");

plt.show()

sns.pairplot(wine_df, diag_kind = "hist", hue = "quality", height = 3, aspect = 1.2, corner = True);
plt.show()

# Include information about values
corr = wine_data.corr()
fig, ax = plt.subplots()
fig.set_size_inches(14, 8)
sns.heatmap(corr, annot=True, fmt=".1f", cmap="RdBu", center=0, ax=ax)

plt.show()

fig, axes = plt.subplots(2, 2, figsize=(15, 10))
axes = axes.flatten()

sns.scatterplot(ax = axes[0],
                x = "residual_sugar",
                y = "quality", hue = "quality",
                data = wine_df).set(title = "Relationship between 'residual_sugar' and 'quality'");

sns.scatterplot(ax = axes[1],
                x = "alcohol",
                y = "quality", hue = "quality",
                data = wine_df).set(title = "Relationship between 'alcohol' and 'quality'");

sns.scatterplot(ax = axes[2],
                x = "pH",
                y = "quality", hue = "quality",
                data = wine_df).set(title = "Relationship between 'pH' and 'quality'");

sns.scatterplot(ax = axes[3],
                x = "density",
                y = "quality", hue = "quality",
                data = wine_df).set(title = "Relationship between 'density' and 'quality'");

plt.show()

sns.scatterplot(x = "residual_sugar",
                y = "pH",
                hue = "quality",
                data = wine_df).set(title = "Relationship between 'residual_sugar' and 'pH'");

sns.scatterplot(x = "alcohol",
                y = "pH",
                hue = "quality",
                palette = "magma",
                data = wine_df).set(title = "Relationship between 'alcohol' and 'pH'");

fig, axes = plt.subplots(nrows = 4, ncols = 3, figsize = (20, 20))

colors = ['#491D8B', '#6929C4', '#8A3FFC', '#A56EFF',
          '#7D3AC1', '#AF4BCE', '#DB4CB2', '#EB548C',
          '#EC96E0', '#A2128E', '#E8D9F3', '#641811']

for index, column in enumerate(wine_df.columns):
    ax = axes.flatten()[index]
    ax.hist(wine_df[column], color = colors[index], label = column)
    ax.legend(loc = "best")
plt.suptitle("Histograms", size = 18)

plt.show()

dataForPlot = wine_df.groupby('quality').mean().total_sulfur_dioxide
fig, ax = plt.subplots()
ax.bar(dataForPlot.index, dataForPlot, color=['C0','C1','C3','C4','C5','C6'])
ax.set_xticks([3, 4, 5, 6, 7, 8])
ax.set_xlabel('Quality')
ax.set_ylabel('Avg. Total Sulfur Dioxide')
plt.show()

dataForPlot = wine_df.groupby('quality').mean().residual_sugar
fig, ax = plt.subplots()
ax.bar(dataForPlot.index, dataForPlot, color=['C0'])
ax.set_xticks([3, 4, 5, 6, 7, 8])
ax.set_xlabel('Quality')
ax.set_ylabel('Avg. Residual Sugar')
plt.show()

wine_df.plot.scatter(x='fixed_acidity', y='pH', legend=False)
plt.show()

dataForPlot = wine_df.groupby('quality').mean().free_sulfur_dioxide
fig, ax = plt.subplots()
ax.bar(dataForPlot.index, dataForPlot, color=['C0'])
ax.set_xticks([3, 4, 5, 6, 7, 8])
ax.set_xlabel('Quality')
ax.set_ylabel('Avg. of free_sulfur_dioxide')
plt.show()

plt.boxplot([wine_df['free_sulfur_dioxide'], wine_df['total_sulfur_dioxide']], vert=False)

plt.xlabel('Sulphur Dioxide')
plt.ylabel('Wine Quality')
plt.title('Free vs Total Sulphur Dioxide in Wine')
plt.yticks([1, 2], ['Free', 'Total'])

plt.show()

# Calculate the sum of density and sum of residual sugar for each row
wine_df['sum_density_residual_sugar'] = wine_df['density'] + wine_df['residual_sugar']

# Create a scatter plot with quality as the color of each point
plt.scatter(wine_df['quality'],wine_df['sum_density_residual_sugar'],  c=wine_df['quality'])
plt.xlabel('Sum of Density and Residual Sugar')
plt.ylabel('Quality')
plt.colorbar()
plt.show()

sns.histplot(data=wine_df, x=wine_df.fixed_acidity, hue="quality", kde=True, bins=20, multiple="stack", alpha=.3)
plt.show()

def quality(variables):
    plt.figure(figsize=(16, 5))
    sns.histplot(data=wine_data, x=variables, hue="quality", kde=True,bins=20)
    if quality == "density": plt.title(f"\n{variables} of red wine\n\n")
    else: plt.title(f"\n{variables} contents in red wine\n\n")
    plt.figtext(0.75, 0.3, f'{wine_data[variables].describe()}')
    sns.despine()

quality("fixed_acidity")
plt.show

<function matplotlib.pyplot.show(close=None, block=None)>

#bar chart of average quantity ordered per country
dataForPlot = wine_data.groupby('quality').mean().residual_sugar
fig, ax = plt.subplots()
ax.barh(dataForPlot.index, dataForPlot, color=['C5', 'C1'])
ax.set_xticklabels(dataForPlot.index, rotation=90)
ax.set_xlabel('Avg. of Residual Sugar')
ax.set_ylabel('Quality')
plt.show()

fig, ax = plt.subplots()
ax.hist(wine_data.density)
ax.set_axisbelow(True)  # Show the grid lines behind the histogram
ax.grid(which='major', color='grey', linestyle='--')
ax.set_xlabel('density')
ax.set_ylabel('count')
plt.show()

# Add the correlation coefficient to the scatterplots above the diagonal
from pandas.plotting import scatter_matrix, parallel_coordinates
df = wine_data[['volatile_acidity', 'sulphates', 'alcohol']]
axes = scatter_matrix(df, alpha=0.5, figsize=(6, 6), diagonal='kde') #kde is for density plots, you can use "hist" for histogram
corr = df.corr().values
for i, j in zip(*plt.np.triu_indices_from(axes, k=1)):
    axes[i, j].annotate("%.3f" %corr[i,j], (0.8, 0.8), xycoords='axes fraction', ha='center', va='center')

plt.show()

fig, axes = plt.subplots(nrows=1, ncols=3)
wine_data.boxplot(column='alcohol', by='quality', ax=axes[0])
wine_data.boxplot(column='volatile_acidity', by='quality', ax=axes[1])
wine_data.boxplot(column='sulphates', by='quality', ax=axes[2])
for ax in axes:
    ax.set_xlabel('quality')
plt.suptitle('')  # Suppress the overall title
plt.tight_layout()  # Increase the separation between the plots

plt.show()

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
0	7.400000	0.700000	0.000000	1.900000	0.076000	11.000000	34.000000	0.997800	3.510000	0.560000	9.400000	5
1	7.800000	0.880000	0.000000	2.600000	0.098000	25.000000	67.000000	0.996800	3.200000	0.680000	9.800000	5
2	7.800000	0.760000	0.040000	2.300000	0.092000	15.000000	54.000000	0.997000	3.260000	0.650000	9.800000	5
3	11.200000	0.280000	0.560000	1.900000	0.075000	17.000000	60.000000	0.998000	3.160000	0.580000	9.800000	6
4	7.400000	0.700000	0.000000	1.900000	0.076000	11.000000	34.000000	0.997800	3.510000	0.560000	9.400000	5
5	7.400000	0.660000	0.000000	1.800000	0.075000	13.000000	40.000000	0.997800	3.510000	0.560000	9.400000	5
6	7.900000	0.600000	0.060000	1.600000	0.069000	15.000000	59.000000	0.996400	3.300000	0.460000	9.400000	5
7	7.300000	0.650000	0.000000	1.200000	0.065000	15.000000	21.000000	0.994600	3.390000	0.470000	10.000000	7
8	7.800000	0.580000	0.020000	2.000000	0.073000	9.000000	18.000000	0.996800	3.360000	0.570000	9.500000	7
9	7.500000	0.500000	0.360000	6.100000	0.071000	17.000000	102.000000	0.997800	3.350000	0.800000	10.500000	5

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
0	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5
1	7.8	0.88	0.00	2.6	0.098	25.0	67.0	0.9968	3.20	0.68	9.8	5
2	7.8	0.76	0.04	2.3	0.092	15.0	54.0	0.9970	3.26	0.65	9.8	5
3	11.2	0.28	0.56	1.9	0.075	17.0	60.0	0.9980	3.16	0.58	9.8	6
4	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
1594	6.2	0.600	0.08	2.0	0.090	32.0	44.0	0.99490	3.45	0.58	10.5	5
1595	5.9	0.550	0.10	2.2	0.062	39.0	51.0	0.99512	3.52	0.76	11.2	6
1596	6.3	0.510	0.13	2.3	0.076	29.0	40.0	0.99574	3.42	0.75	11.0	6
1597	5.9	0.645	0.12	2.0	0.075	32.0	44.0	0.99547	3.57	0.71	10.2	5
1598	6.0	0.310	0.47	3.6	0.067	18.0	42.0	0.99549	3.39	0.66	11.0	6

	count	mean	std	min	25%	50%	75%	max
fixed_acidity	1599.000000	8.319637	1.741096	4.600000	7.100000	7.900000	9.200000	15.900000
volatile_acidity	1599.000000	0.527821	0.179060	0.120000	0.390000	0.520000	0.640000	1.580000
citric_acid	1599.000000	0.270976	0.194801	0.000000	0.090000	0.260000	0.420000	1.000000
residual_sugar	1599.000000	2.538806	1.409928	0.900000	1.900000	2.200000	2.600000	15.500000
chlorides	1599.000000	0.087467	0.047065	0.012000	0.070000	0.079000	0.090000	0.611000
free_sulfur_dioxide	1599.000000	15.874922	10.460157	1.000000	7.000000	14.000000	21.000000	72.000000
total_sulfur_dioxide	1599.000000	46.467792	32.895324	6.000000	22.000000	38.000000	62.000000	289.000000
density	1599.000000	0.996747	0.001887	0.990070	0.995600	0.996750	0.997835	1.003690
pH	1599.000000	3.311113	0.154386	2.740000	3.210000	3.310000	3.400000	4.010000
sulphates	1599.000000	0.658149	0.169507	0.330000	0.550000	0.620000	0.730000	2.000000
alcohol	1599.000000	10.422983	1.065668	8.400000	9.500000	10.200000	11.100000	14.900000
quality	1599.000000	5.636023	0.807569	3.000000	5.000000	6.000000	6.000000	8.000000

Tổng quan về Tập dữ liệu Chất lượng Rượu¶

Nội dung Dữ liệu¶

Các Biến Đầu vào (Input Variables - Dựa trên kiểm tra lý hóa)¶

Tính chất của Tập dữ liệu và Ứng dụng¶